Prediction of Hereditary Cancers Using Neural Networks

Family history is a major risk factor for many types of cancer. Mendelian risk prediction models translate family histories into cancer risk predictions based on knowledge of cancer susceptibility genes. These models are widely used in clinical practice to help identify high-risk individuals. Mendelian models leverage the entire family history, but they rely on many assumptions about cancer susceptibility genes that are either unrealistic or challenging to validate due to low mutation prevalence. Training more flexible models, such as neural networks, on large databases of pedigrees can potentially lead to accuracy gains. In this paper, we develop a framework to apply neural networks to family history data and investigate their ability to learn inherited susceptibility to cancer. While there is an extensive literature on neural networks and their state-of-the-art performance in many tasks, there is little work applying them to family history data. We propose adaptations of fully-connected neural networks and convolutional neural networks to pedigrees. In data simulated under Mendelian inheritance, we demonstrate that our proposed neural network models are able to achieve nearly optimal prediction performance. Moreover, when the observed family history includes misreported cancer diagnoses, neural networks are able to outperform the Mendelian BRCAPRO model embedding the correct inheritance laws. Using a large dataset of over 200,000 family histories, the Risk Service cohort, we train prediction models for future risk of breast cancer. We validate the models using data from the Cancer Genetics Network.

[1]  R. Green,et al.  A Comparison of Multi-Layer Neural Network and Logistic Regression in Hereditary Non-Polyposis Colorectal Cancer Risk Assessment , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[2]  Tianxi Cai,et al.  Evaluating Prediction Rules for t-Year Survivors With Censored Regression Models , 2007 .

[3]  G. Parmigiani,et al.  Whole pelvic helical tomotherapy for locally advanced cervical cancer: technical implementation of IMRT with helical tomothearapy , 2009, Radiation oncology.

[4]  R. Goldbohm,et al.  Familial breast cancer: collaborative reanalysis of individual data from 52 epidemiological studies including 58 209 women with breast cancer and 101 986 women without the disease , 2001, The Lancet.

[5]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[6]  M. Gail,et al.  Projecting individualized probabilities of developing breast cancer for white females who are being examined annually. , 1989, Journal of the National Cancer Institute.

[7]  Giovanni Parmigiani,et al.  Providing access to risk prediction tools via the HL7 XML-formatted risk web service , 2013, Breast Cancer Research and Treatment.

[8]  D. Thomas,et al.  Bias and efficiency in family-based gene-characterization studies: conditional, prospective, retrospective, and joint likelihoods. , 2000, American journal of human genetics.

[9]  Karla Kerlikowske,et al.  Using Clinical Factors and Mammographic Breast Density to Estimate Breast Cancer Risk: Development and Validation of a New Predictive Model , 2008, Annals of Internal Medicine.

[10]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[12]  L. Cannon-Albright,et al.  Population-Based Relative Risks for Lung Cancer Based on Complete Family History of Lung Cancer. , 2018, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[13]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[14]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  D. Easton How many more breast cancer predisposition genes are there? , 1999, Breast Cancer Research.

[17]  Hormuzd A Katki,et al.  Effect of Misreported Family History on Mendelian Mutation Prediction Models , 2006, Biometrics.

[18]  Barak A. Pearlmutter,et al.  Equivalence Proofs for Multi-Layer Perceptron Classifiers and the Bayesian Discriminant Function , 1991 .

[19]  Mitchell H Gail,et al.  Projecting Individualized Absolute Invasive Breast Cancer Risk in US Hispanic Women , 2017, Journal of the National Cancer Institute.

[20]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[21]  M. Schumacher,et al.  Consistent Estimation of the Expected Brier Score in General Survival Models with Right‐Censored Event Times , 2006, Biometrical journal. Biometrische Zeitschrift.

[22]  John P. A. Ioannidis,et al.  An empirical assessment of validation practices for molecular classifiers , 2011, Briefings Bioinform..

[23]  Hang Su,et al.  Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples , 2017, ArXiv.

[24]  Giovanni Parmigiani,et al.  Estimating CDKN2A carrier probability and personalizing cancer risk assessments in hereditary melanoma using MelaPRO. , 2010, Cancer research.

[25]  Prakash Nadkarni,et al.  The Cancer Genetics Network: Recruitment Results and Pilot Studies , 2003, Public Health Genomics.

[26]  Keechul Jung,et al.  GPU implementation of neural networks , 2004, Pattern Recognit..

[27]  Quanshi Zhang,et al.  Interpretable Convolutional Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[28]  G. Lenoir,et al.  Pretest prediction of BRCA1 or BRCA2 mutation by risk counselors and the computer model BRCAPRO. , 2002, Journal of the National Cancer Institute.

[29]  Danielle Braun,et al.  Nonparametric Adjustment for Measurement Error in Time-to-Event Data: Application to Risk Prediction Models , 2018, Journal of the American Statistical Association.

[30]  J. Jonsson,et al.  Electronically ascertained extended pedigrees in breast cancer genetic counseling , 2018, Familial Cancer.

[31]  K. Hemminki,et al.  Modification of cancer risks in offspring by sibling and parental cancers from 2,112,616 nuclear families , 2001, International journal of cancer.

[32]  G. Pichert,et al.  Evidence-based management options for women at increased breast/ovarian cancer risk. , 2003, Annals of oncology : official journal of the European Society for Medical Oncology.

[33]  C. Bonaïti‐pellié,et al.  Estimating penetrance from family data using a retrospective likelihood when ascertainment depends on genotype and age of onset , 2004, Genetic epidemiology.

[34]  R. Barzilay,et al.  A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction. , 2019, Radiology.

[35]  Argyrios Ziogas,et al.  Validation of family history data in cancer family registries. , 2003, American journal of preventive medicine.

[36]  Cynthia Rudin,et al.  Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains its Predictions , 2017, AAAI.

[37]  Stephen W Duffy,et al.  A breast cancer prediction model incorporating familial and personal risk factors , 2004, Hereditary Cancer in Clinical Practice.

[38]  Danielle Braun,et al.  Extending Mendelian Risk Prediction Models to Handle Misreported Family History , 2014 .

[39]  G. Ginsburg,et al.  Family health history: underused for actionable risk assessment , 2019, The Lancet.

[40]  Melissa Bondy,et al.  Projecting individualized absolute invasive breast cancer risk in African American women. , 2007, Journal of the National Cancer Institute.

[41]  Anne-Laure Boulesteix,et al.  Cross-study validation for the assessment of prediction algorithms , 2014, Bioinform..

[42]  D. Gudbjartsson,et al.  Cancer as a Complex Phenotype: Pattern of Cancer Distribution within and beyond the Nuclear Family , 2004, PLoS medicine.

[43]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[44]  Gord Glendon,et al.  10-year performance of four models of breast cancer risk: a validation study. , 2019, The Lancet. Oncology.

[45]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[46]  Yotam Hechtlinger,et al.  A Generalization of Convolutional Neural Networks to Graph-Structured Data , 2017, ArXiv.

[47]  Lorenzo Trippa,et al.  Bayesian nonparametric cross-study validation of prediction methods , 2015, 1506.00474.

[48]  J. Jonsson,et al.  The use of genealogy databases for risk assessment in genetic health service: a systematic review , 2012, Journal of Community Genetics.

[49]  Zoe Guan,et al.  Performance of breast cancer risk assessment models in a large mammography cohort. , 2019, Journal of the National Cancer Institute.

[50]  D. Easton,et al.  The BOADICEA model of genetic susceptibility to breast and ovarian cancer , 2004, British Journal of Cancer.

[51]  Wojciech Czarnecki,et al.  On Loss Functions for Deep Neural Networks in Classification , 2017, ArXiv.

[52]  N Risch,et al.  Autosomal dominant inheritance of early‐onset breast cancer. Implications for risk prediction , 1994, Cancer.

[53]  R. Barzilay,et al.  Deep Learning Model to Assess Cancer Risk on the Basis of a Breast MR Image Alone. , 2019, AJR. American journal of roentgenology.

[54]  Giovanni Parmigiani,et al.  Simplifying clinical use of the genetic risk prediction model BRCAPRO , 2013, Breast Cancer Research and Treatment.

[55]  Danielle Braun,et al.  Penetrance of Breast and Ovarian Cancer in Women Who Carry a BRCA1/2 Mutation and Do Not Use Risk-Reducing Salpingo-Oophorectomy: An Updated Meta-Analysis , 2020, JNCI cancer spectrum.

[56]  Norman Boyd,et al.  The Breast Cancer Family Registry: an infrastructure for cooperative multinational, interdisciplinary and translational studies of the genetic epidemiology of breast cancer , 2004, Breast Cancer Research.

[57]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[58]  N. Risch,et al.  Autosomal dominant inheritance of early‐onset breast cancer. Implications for risk prediction , 1994 .

[59]  Yujian Li,et al.  A concatenating framework of shortcut convolutional neural networks , 2017, ArXiv.

[60]  Ewout W Steyerberg,et al.  Prediction of MLH1 and MSH2 mutations in Lynch syndrome. , 2006, JAMA.

[61]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[62]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[63]  Y Vergouwe,et al.  Updating methods improved the performance of a clinical prediction model in new patients. , 2008, Journal of clinical epidemiology.

[64]  A. Ashworth,et al.  The Breakthrough Generations Study: design of a long-term UK cohort study to investigate breast cancer aetiology , 2011, British Journal of Cancer.

[65]  Jack Cuzick,et al.  A breast cancer prediction model incorporating familial and personal risk factors , 2012 .

[66]  L. Cannon-Albright,et al.  A comprehensive survey of cancer risks in extended families , 2012, Genetics in Medicine.

[67]  D. Berry,et al.  Probability of carrying a mutation of breast-ovarian cancer gene BRCA1 based on family history. , 1997, Journal of the National Cancer Institute.

[68]  Karl W Broman,et al.  BayesMendel: an R Environment for Mendelian Risk Prediction , 2004, Statistical applications in genetics and molecular biology.

[69]  Jungyeon Choi,et al.  A comparison of different methods to handle missing data in the context of propensity score analysis , 2018, European Journal of Epidemiology.

[70]  Steven E. Bayer,et al.  A strong candidate for the breast and ovarian cancer susceptibility gene BRCA1. , 1994, Science.

[71]  Megan Doerr,et al.  Review and Comparison of Electronic Patient-Facing Family Health History Tools , 2018, Journal of Genetic Counseling.

[72]  M. García-Closas,et al.  Comparative validation of breast cancer risk prediction models and projections for future risk stratification , 2018, bioRxiv.

[73]  Mathias Niepert,et al.  Learning Convolutional Neural Networks for Graphs , 2016, ICML.

[74]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[75]  Giovanni Parmigiani,et al.  PancPRO: risk assessment for individuals with a family history of pancreatic cancer. , 2007, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[76]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[77]  Giovanni Parmigiani,et al.  Meta-analysis of BRCA1 and BRCA2 penetrance. , 2007, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[78]  Konstantin Strauch,et al.  Breast cancer risk assessment across the risk continuum: genetic and nongenetic risk factors contributing to differential model performance , 2012, Breast Cancer Research.

[79]  John D Potter,et al.  Colon Cancer Family Registry: An International Resource for Studies of the Genetic Epidemiology of Colon Cancer , 2007, Cancer Epidemiology Biomarkers & Prevention.

[80]  C. Bonaïti‐pellié,et al.  ARCAD: A method for estimating age‐dependent disease risk associated with mutation carrier status from family data , 1995, Genetic epidemiology.

[81]  Julian Peto,et al.  Identification of the breast cancer susceptibility gene BRCA2 , 1996, Nature.

[82]  Aníbal R. Figueiras-Vidal,et al.  Pattern classification with missing data: a review , 2010, Neural Computing and Applications.

[83]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[84]  N E Day,et al.  A comprehensive model for familial breast cancer incorporating BRCA1, BRCA2 and other genes , 2002, British Journal of Cancer.

[85]  Bernhard Schölkopf,et al.  Domain Adaptation under Target and Conditional Shift , 2013, ICML.

[86]  Kenneth D. Mandl,et al.  SMART on FHIR: a standards-based, interoperable apps platform for electronic health records , 2016, J. Am. Medical Informatics Assoc..

[87]  Nilanjan Chatterjee,et al.  iCARE: R package to build, validate and apply absolute risk models , 2016, bioRxiv.

[88]  W. Knaus,et al.  A Case-Control Study to Add Volumetric or Clinical Mammographic Density into the Tyrer-Cuzick Breast Cancer Risk Model , 2019, Journal of breast imaging.

[89]  Mitchell H Gail,et al.  Projecting individualized absolute invasive breast cancer risk in Asian and Pacific Islander American women. , 2011, Journal of the National Cancer Institute.

[90]  D. Berry,et al.  Determining carrier probabilities for breast cancer-susceptibility genes BRCA1 and BRCA2. , 1998, American journal of human genetics.

[91]  L. Briollais,et al.  Estimating Disease Risk Associated with Mutated Genes in Family-Based Designs , 2008, Human Heredity.

[92]  D. Seminara,et al.  Pancreatic Cancer Genetic Epidemiology Consortium , 2006, Cancer Epidemiology Biomarkers & Prevention.

[93]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[94]  R. Elston,et al.  A general model for the genetic analysis of pedigree data. , 1971, Human heredity.

[95]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[96]  Ge Wang,et al.  On Interpretability of Artificial Neural Networks , 2020, ArXiv.

[97]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[98]  Mikhail Belkin,et al.  Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks , 2020, ICLR.

[99]  N. Obuchowski,et al.  Assessing the Performance of Prediction Models: A Framework for Traditional and Novel Measures , 2010, Epidemiology.

[100]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[101]  Andrew W. Roddam,et al.  Measurement Error in Nonlinear Models: a Modern Perspective , 2008 .